© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30969
    Prev
    Next
    INDEX
    Explanations

    references to waves in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.15
    0.9%
    466
    +0.14
    0.8%
    246
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.15
    0.02
    115
    +0.14
    0.01
    210
    +0.12
    0.01
    Negative Logits
    ľĵ
    -1.70
    ĥ½
    -1.65
    iquit
    -1.65
     accordance
    -1.63
    ificantly
    -1.61
    etheless
    -1.57
    >()
    -1.52
    achelor
    -1.51
     afford
    -1.50
    ©
    -1.47
    POSITIVE LOGITS
    fulness
    1.97
    front
    1.85
    ings
    1.85
    maker
    1.83
    gun
    1.83
    ppler
    1.74
    heads
    1.73
    iness
    1.72
    waves
    1.67
    walker
    1.67
    Activations Density 0.153%

    No Known Activations